Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/dromara/liteflow/agents-mdgit clone --depth 1 https://github.com/dromara/liteflowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02667 | $0.02667 |
| Opus 5 | $0.01333 | $0.01333 |
| Sonnet 5 | $0.00533 | $0.00533 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
liteflow AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Overview
LiteFlow (v2.16.1) is a lightweight rules engine framework for complex component-based business orchestration. It uses a DSL to drive workflows with support for hot reload and 11 scripting languages. The project targets Java 8+ (up to JDK 25) and has 2000+ test cases.
Official Documentation: https://liteflow.cc/pages/5816c5/
Commands
Build
# Build entire project (uses 'compile' profile by default, includes test modules)
mvn clean package -DskipTests
# Build with tests
mvn clean package
# Build specific module
mvn clean package -DskipTests -pl liteflow-core
# Build for release (production modules only, excludes tests)
mvn clean package -DskipTests -P release
Run Tests
# Run all tests
mvn test
# Run tests for specific module (30+ test modules in liteflow-testcase-el/)
mvn test -pl liteflow-testcase-el/liteflow-testcase-el-springboot
# Run single test class
mvn test -pl liteflow-core -Dtest=FlowExecutorTest
# Run specific test method
mvn test -pl liteflow-core -Dtest=FlowExecutorTest#testExecute
Other Commands
# Dependency tree
mvn dependency:tree
# View module structure
ls liteflow-*/pom.xml
High-Level Architecture
Core Execution Model
FlowExecutor → Chain → Condition Tree → Node Components
- FlowExecutor: Entry point for executing workflows (
execute2Resp(chainId, param)) - FlowBus: Central metadata registry for all chains and nodes (thread-safe, supports hot reload)
- Chain: Named workflow composed of an EL expression that compiles to a Condition tree
- Slot/DataBus: Thread-safe context management using slot pooling (configurable
slotSize) - NodeComponent: Base class for all business logic components
Key Architectural Patterns
1. Two-Stage Parsing
Chains are built in two phases to handle circular dependencies:
- Phase 1: Register chain IDs (creates placeholder chains)
- Phase 2: Build complete condition trees with EL parsing
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 247 lines · 2,667 tokens per session scan A 68ea36d4446d
liteflow AGENTS.md is an instructions file published in the GitHub repository dromara/liteflow (3,837 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,667 tokens to every session, about $0.0133 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Blaze CLAUDE.md
Claude Code instructions for grloper/Blaze, covering claude.md, what this is, commands, architecture (the big picture) and invariants you must not break.
MPS AGENTS.md
Instructions for JetBrains/MPS, covering agents guide for this project, ⚠️ warning: never read raw mps model files, project nature: jvm + mps, choose tools by task and rules for java/kotlin work.
react-nprogress AGENTS.md
Instructions for tanem/react-nprogress, covering agent instructions for react-nprogress, project, key commands, code standards and comments.
onebase CLAUDE.md
Instructions for ivanarama/onebase, covering claude.md, сборка и запуск, cli + сервер (без cgo) — основной бинарь, gui с нативным окном (cgo + webview2 на windows) and тесты.
allo AGENTS.md
Instructions for cornell-zhang/allo, covering building, testing, code style and don'ts.
react-native-typescript-library-starter AGENTS.md
Instructions for kuraydev/react-native-typescript-library-starter, covering agents.md — ai agent instructions, project overview, directory map, commands and conventions.